Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to data access and privacy concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    醐
    -0.40
    庁
    -0.35
    InitVars
    -0.33
     معن
    -0.32
    liev
    -0.32
    couraged
    -0.31
    roned
    -0.30
    mel
    -0.30
    wkt
    -0.30
    courage
    -0.29
    POSITIVE LOGITS
     profiling
    0.68
     dành
    0.66
     tungkol
    0.65
     biographical
    0.65
     depicting
    0.63
    關於
    0.63
     praising
    0.62
     describing
    0.62
     about
    0.61
    ISupport
    0.60
    Act Density 0.775%

    No Known Activations